Optimizing 3D object detection for embedded systems in automated vehicles using sensor data fusion and CUDA computing

Topi Miekkala, Matti Kutila, Mathias Schneider, Alfred Höß

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

22 Downloads (Pure)

Abstract

This article explores the utilization of the processing power of GPUs using CUDA computation for real-time aggregation of multi-sensor data and detection of 3D objects using parallel clustering algorithms. The purpose is to implement an algorithm that fuses raw lidar point cloud data and 2D camera image object detections to produce 3D object clusters in a lidar point cloud. Most of the computation has been implemented using CUDA parallelism to investigate the capability of GPU devices in this task, which is a common challenge in automated driving. The results indicate that processing times can be optimized within the algorithm, which is crucial when considering the large amounts of data provided by lidar and camera-based systems. The algorithm can perform inference on the Jetson Xavier AGX at rates of ~20 to ~220 ms depending on the number of objects and their corresponding point amounts in the KITTI dataset.
Original languageEnglish
Title of host publication2022 IEEE 18th International Conference on Intelligent Computer Communication and Processing (ICCP)
PublisherIEEE Institute of Electrical and Electronic Engineers
Number of pages6
Publication statusAccepted/In press - 22 Sep 2022
MoE publication typeA4 Article in a conference publication
Event2022 IEEE 18th International Conference on Intelligent Computer Communication and Processing, ICCP 2022 - Cluj-Napoca, Romania
Duration: 22 Sep 202224 Sep 2022

Conference

Conference2022 IEEE 18th International Conference on Intelligent Computer Communication and Processing, ICCP 2022
Country/TerritoryRomania
CityCluj-Napoca
Period22/09/2224/09/22

Fingerprint

Dive into the research topics of 'Optimizing 3D object detection for embedded systems in automated vehicles using sensor data fusion and CUDA computing'. Together they form a unique fingerprint.

Cite this